Nemotron 3.5 Lightning
AI model by NVIDIA. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Nemotron 3.5 Lightning is a budget-tier option from NVIDIA at $0.22/M output tokens. Despite the low price, it scores competitively on Coding Index (26.8) and Intelligence Index (23.6) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Nemotron 3.5 Lightning reports 302 tok/s output speed and 1160ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, Nemotron 3.5 Lightning costs $0.09 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Nemotron 3.5 LightningCurrent | $0.07 | $0.22 | 302 tok/s |
| Ling 3.0 Flash | $0.07 | $0.22 | — |
| Hy3-preview (Reasoning) | $0.06 | $0.21 | — |
| Hy3-preview (Non-reasoning) | $0.06 | $0.21 | — |
| gpt-oss-20b (low) | $0.07 | $0.20 | 170 tok/s |
| Qwen3.5 9B (Reasoning) | $0.14 | $0.20 | 81 tok/s |